all AI news
The N+ Implementation Details of RLHF with PPO: A Case Study on TL;DR Summarization
March 27, 2024, 4:41 a.m. | Shengyi Huang, Michael Noukhovitch, Arian Hosseini, Kashif Rasul, Weixun Wang, Lewis Tunstall
cs.LG updates on arXiv.org arxiv.org
Abstract: This work is the first to openly reproduce the Reinforcement Learning from Human Feedback (RLHF) scaling behaviors reported in OpenAI's seminal TL;DR summarization work. We create an RLHF pipeline from scratch, enumerate over 20 key implementation details, and share key insights during the reproduction. Our RLHF-trained Pythia models demonstrate significant gains in response quality that scale with model size, with our 2.8B, 6.9B models outperforming OpenAI's released 1.3B checkpoint. We publicly release the trained model …
arxiv case case study cs.lg implementation ppo rlhf study summarization type
More from arxiv.org / cs.LG updates on arXiv.org
Jobs in AI, ML, Big Data
AI Research Scientist
@ Vara | Berlin, Germany and Remote
Data Architect
@ University of Texas at Austin | Austin, TX
Data ETL Engineer
@ University of Texas at Austin | Austin, TX
Lead GNSS Data Scientist
@ Lurra Systems | Melbourne
Data Science Analyst
@ Mayo Clinic | AZ, United States
Sr. Data Scientist (Network Engineering)
@ SpaceX | Redmond, WA